Upgrade to new WebGPU EP

* ONNX Runtime improvements (experimental native webgpu; fix iOS) (#1231)

* customize the wasm paths

* update implementation

* allow using 'webgpu' in nodejs binding

* update version of onnxruntime-node

* Upgrade onnxruntime-web to same version as onnxruntime-node

* Update list of supported devices

---------

Co-authored-by: Joshua Lochner <[email protected]>

* customize the wasm paths (#1250)

* customize the wasm paths

* update implementation

* [internal] Add is_decoder option to session retrieval for preferred output location

* Update tests

* Formatting

* Bump ort versions

* Bump onnxruntime-node version

* Bump versions

* Bump ORT versions

* Bump versions

* Only check webgpu fp16 for non-node environments

* Fix

* Assume node supports webgpu

* Update ORT node support comment

* Relax test strictness

* Update conversion script versions

* Downgrade onnxslim

* cleanup

* Update package-lock.json

* Update onnxruntime versions

* Update post-build script

* Use built-in session release function

* Call garbage collection after each tokenizer test

* Do not double-throw error

* Fix race-condition in build process with file removal

* Update versions

* Bump jinja version

* [version] Update to 3.6.3

* Bump jinja version to support new features

* [version] Update to 3.6.3

* Add support for LFM2 models (#1367)

* Use prefix in lfm2 output location (#1369)

* Update package-lock.json

* Run `npm audit fix`

* Add special tokens in text-generation pipeline if tokenizer requires (#1370)

* Add special tokens in text-generation pipeline if tokenizer requires

* Fix logits processors tests

* Update bundles.test.js

* Update comment

* Formatting

* Add support for ModernBERT Decoder (#1371)

* Use from/to buffer instead of string

Actually fixes #1343

* Add support for Voxtral (#1373)

* Support longform voxtral processing (#1375)

* [version] Update to 3.7.0

* Add support for Arcee (#1377)

* Optimize tensor.slice() (#1381)

* Optimize tensor.slice()

The performance of executing `tensor.slice()` is super poor, especially for
the 'logits' tensor with large dimensions.

```
const logits = outputs.logits.slice(null, -1, null);`
```

This is because currently implementation of the `slice` method manually iterates
through each element and calculate indices which is a big time consuming if
the tensor shape is large.

For cases like `slice(null, -1, null)`, where the slicing operation is
contiguous along certain dimensions, which can be optimized by bulk copy
by using `TypeArray.subarray()` and `TypeArray.set()`.

* nit

* Add a few more tensor slice unit tests

---------

Co-authored-by: Joshua Lochner <[email protected]>

---------

Co-authored-by: Yulong Wang <[email protected]>
Co-authored-by: Wanming Lin <[email protected]>

Author: 3 people

README.md

@@ -47,7 +47,7 @@ npm i @huggingface/transformers
 Alternatively, you can use it in vanilla JS, without any bundler, by using a CDN or static hosting. For example, using [ES Modules](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Modules), you can import the library with:
 ```html
 <script type="module">
-    import { pipeline } from 'https://cdn.jsdelivr.net/npm/@huggingface/transformers@3.6.2';
+    import { pipeline } from 'https://cdn.jsdelivr.net/npm/@huggingface/transformers@3.7.0';
 </script>
 ```
 
@@ -155,7 +155,7 @@ Check out the Transformers.js [template](https://huggingface.co/new-space?templa
 
 
 
-By default, Transformers.js uses [hosted pretrained models](https://huggingface.co/models?library=transformers.js) and [precompiled WASM binaries](https://cdn.jsdelivr.net/npm/@huggingface/transformers@3.6.2/dist/), which should work out-of-the-box. You can customize this as follows:
+By default, Transformers.js uses [hosted pretrained models](https://huggingface.co/models?library=transformers.js) and [precompiled WASM binaries](https://cdn.jsdelivr.net/npm/@huggingface/transformers@3.7.0/dist/), which should work out-of-the-box. You can customize this as follows:
 
 ### Settings
 
@@ -288,6 +288,7 @@ You can refine your search by selecting the task you're interested in (e.g., [te
 ### Models
 
 1. **[ALBERT](https://huggingface.co/docs/transformers/model_doc/albert)** (from Google Research and the Toyota Technological Institute at Chicago) released with the paper [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://huggingface.co/papers/1909.11942), by Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut.
+1. **[Arcee](https://huggingface.co/docs/transformers/model_doc/arcee)** (from Arcee AI) released with the blog post [Announcing Arcee Foundation Models](https://www.arcee.ai/blog/announcing-the-arcee-foundation-model-family) by Fernando Fernandes, Varun Singh, Charles Goddard, Lucas Atkins, Mark McQuade, Maziyar Panahi, Conner Stewart, Colin Kealty, Raghav Ravishankar, Lucas Krauss, Anneketh Vij, Pranav Veldurthi, Abhishek Thakur, Julien Simon, Scott Zembsch, Benjamin Langer, Aleksiej Cecocho, Maitri Patel.
 1. **[Audio Spectrogram Transformer](https://huggingface.co/docs/transformers/model_doc/audio-spectrogram-transformer)** (from MIT) released with the paper [AST: Audio Spectrogram Transformer](https://huggingface.co/papers/2104.01778) by Yuan Gong, Yu-An Chung, James Glass.
 1. **[BART](https://huggingface.co/docs/transformers/model_doc/bart)** (from Facebook) released with the paper [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://huggingface.co/papers/1910.13461) by Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov and Luke Zettlemoyer.
 1. **[BEiT](https://huggingface.co/docs/transformers/model_doc/beit)** (from Microsoft) released with the paper [BEiT: BERT Pre-Training of Image Transformers](https://huggingface.co/papers/2106.08254) by Hangbo Bao, Li Dong, Furu Wei.
@@ -355,6 +356,7 @@ You can refine your search by selecting the task you're interested in (e.g., [te
 1. **JinaCLIP** (from Jina AI) released with the paper [Jina CLIP: Your CLIP Model Is Also Your Text Retriever](https://huggingface.co/papers/2405.20204) by Andreas Koukounas, Georgios Mastrapas, Michael Günther, Bo Wang, Scott Martens, Isabelle Mohr, Saba Sturua, Mohammad Kalim Akram, Joan Fontanals Martínez, Saahil Ognawala, Susana Guzman, Maximilian Werk, Nan Wang, Han Xiao.
 1. **LiteWhisper** (from University of Washington, Kotoba Technologies) released with the paper [LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation](https://huggingface.co/papers/2502.20583) by Keisuke Kamahori, Jungo Kasai, Noriyuki Kojima, Baris Kasikci.
 1. **[LongT5](https://huggingface.co/docs/transformers/model_doc/longt5)** (from Google AI) released with the paper [LongT5: Efficient Text-To-Text Transformer for Long Sequences](https://huggingface.co/papers/2112.07916) by Mandy Guo, Joshua Ainslie, David Uthus, Santiago Ontanon, Jianmo Ni, Yun-Hsuan Sung, Yinfei Yang.
+1. **[LFM2](https://huggingface.co/docs/transformers/model_doc/lfm2)** (from Liquid AI) released with the blog post [Introducing LFM2: The Fastest On-Device Foundation Models on the Market](https://www.liquid.ai/blog/liquid-foundation-models-v2-our-second-series-of-generative-ai-models) by the Liquid AI Team.
 1. **[LLaMA](https://huggingface.co/docs/transformers/model_doc/llama)** (from The FAIR team of Meta AI) released with the paper [LLaMA: Open and Efficient Foundation Language Models](https://huggingface.co/papers/2302.13971) by Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, Guillaume Lample.
 1. **[Llama2](https://huggingface.co/docs/transformers/model_doc/llama2)** (from The FAIR team of Meta AI) released with the paper [Llama2: Open Foundation and Fine-Tuned Chat Models](https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/XXX) by Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller, Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez Madian Khabsa, Isabel Kloumann, Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov, Pushka rMishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith, Ranjan Subramanian, Xiaoqing EllenTan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu, Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan, Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, Thomas Scialom.
 1. **[LLaVa](https://huggingface.co/docs/transformers/model_doc/llava)** (from Microsoft Research & University of Wisconsin-Madison) released with the paper [Visual Instruction Tuning](https://huggingface.co/papers/2304.08485) by Haotian Liu, Chunyuan Li, Yuheng Li and Yong Jae Lee.
@@ -381,6 +383,7 @@ You can refine your search by selecting the task you're interested in (e.g., [te
 1. **[MobileViT](https://huggingface.co/docs/transformers/model_doc/mobilevit)** (from Apple) released with the paper [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://huggingface.co/papers/2110.02178) by Sachin Mehta and Mohammad Rastegari.
 1. **[MobileViTV2](https://huggingface.co/docs/transformers/model_doc/mobilevitv2)** (from Apple) released with the paper [Separable Self-attention for Mobile Vision Transformers](https://huggingface.co/papers/2206.02680) by Sachin Mehta and Mohammad Rastegari.
 1. **[ModernBERT](https://huggingface.co/docs/transformers/model_doc/modernbert)** (from Answer.AI and LightOn) released with the paper [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://huggingface.co/papers/2412.13663) by Benjamin Warner, Antoine Chaffin, Benjamin Clavié, Orion Weller, Oskar Hallström, Said Taghadouini, Alexis Gallagher, Raja Biswas, Faisal Ladhak, Tom Aarsen, Nathan Cooper, Griffin Adams, Jeremy Howard, Iacopo Poli.
+1. **[ModernBERT Decoder](https://huggingface.co/docs/transformers/model_doc/modernbert-decoder)** (from Johns Hopkins University and LightOn) released with the paper [Seq vs Seq: An Open Suite of Paired Encoders and Decoders](https://huggingface.co/papers/2507.11412) by Orion Weller, Kathryn Ricci, Marc Marone, Antoine Chaffin, Dawn Lawrie, Benjamin Van Durme.
 1. **Moondream1** released in the repository [moondream](https://github.com/vikhyat/moondream) by vikhyat.
 1. **[Moonshine](https://huggingface.co/docs/transformers/model_doc/moonshine)** (from Useful Sensors) released with the paper [Moonshine: Speech Recognition for Live Transcription and Voice Commands](https://huggingface.co/papers/2410.15608) by Nat Jeffries, Evan King, Manjunath Kudlur, Guy Nicholson, James Wang, Pete Warden.
 1. **[MPNet](https://huggingface.co/docs/transformers/model_doc/mpnet)** (from Microsoft Research) released with the paper [MPNet: Masked and Permuted Pre-training for Language Understanding](https://huggingface.co/papers/2004.09297) by Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, Tie-Yan Liu.
@@ -439,6 +442,7 @@ You can refine your search by selecting the task you're interested in (e.g., [te
 1. **[ViTMSN](https://huggingface.co/docs/transformers/model_doc/vit_msn)** (from Meta AI) released with the paper [Masked Siamese Networks for Label-Efficient Learning](https://huggingface.co/papers/2204.07141) by Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Florian Bordes, Pascal Vincent, Armand Joulin, Michael Rabbat, Nicolas Ballas.
 1. **[ViTPose](https://huggingface.co/docs/transformers/model_doc/vitpose)** (from The University of Sydney) released with the paper [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://huggingface.co/papers/2204.12484) by Yufei Xu, Jing Zhang, Qiming Zhang, Dacheng Tao.
 1. **[VITS](https://huggingface.co/docs/transformers/model_doc/vits)** (from Kakao Enterprise) released with the paper [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://huggingface.co/papers/2106.06103) by Jaehyeon Kim, Jungil Kong, Juhee Son.
+1. **[Voxtral](https://huggingface.co/docs/transformers/model_doc/voxtral)** (from Mistral AI) released with the paper [Voxtral](https://huggingface.co/papers/2507.13264) by Alexander H. Liu, Andy Ehrenberg, Andy Lo, Clément Denoix, Corentin Barreau, Guillaume Lample, Jean-Malo Delignon, Khyathi Raghavi Chandu, Patrick von Platen, Pavankumar Reddy Muddireddy, Sanchit Gandhi, Soham Ghosh, Srijan Mishra, Thomas Foubert, Abhinav Rastogi, Adam Yang, Albert Q. Jiang, Alexandre Sablayrolles, Amélie Héliou, Amélie Martin, Anmol Agarwal, Antoine Roux, Arthur Darcet, Arthur Mensch, Baptiste Bout, Baptiste Rozière, Baudouin De Monicault, Chris Bamford, Christian Wallenwein, Christophe Renaudin, Clémence Lanfranchi, Darius Dabert, Devendra Singh Chaplot, Devon Mizelle, Diego de las Casas, Elliot Chane-Sane, Emilien Fugier, Emma Bou Hanna, Gabrielle Berrada, Gauthier Delerce, Gauthier Guinet, Georgii Novikov, Guillaume Martin, Himanshu Jaju, Jan Ludziejewski, Jason Rute, Jean-Hadrien Chabran, Jessica Chudnovsky, Joachim Studnia, Joep Barmentlo, Jonas Amar, Josselin Somerville Roberts, Julien Denize, Karan Saxena, Karmesh Yadav, Kartik Khandelwal, Kush Jain, Lélio Renard Lavaud, Léonard Blier, Lingxiao Zhao, Louis Martin, Lucile Saulnier, Luyu Gao, Marie Pellat, Mathilde Guillaumin, Mathis Felardos, Matthieu Dinot, Maxime Darrin, Maximilian Augustin, Mickaël Seznec, Neha Gupta, Nikhil Raghuraman, Olivier Duchenne, Patricia Wang, Patryk Saffer, Paul Jacob, Paul Wambergue, Paula Kurylowicz, Philomène Chagniot, Pierre Stock, Pravesh Agrawal, Rémi Delacourt, Romain Sauvestre, Roman Soletskyi, Sagar Vaze, Sandeep Subramanian, Saurabh Garg, Shashwat Dalal, Siddharth Gandhi, Sumukh Aithal, Szymon Antoniak, Teven Le Scao, Thibault Schueller, Thibaut Lavril, Thomas Robert, Thomas Wang, Timothée Lacroix, Tom Bewley, Valeriia Nemychnikova, Victor Paltz , Virgile Richard, Wen-Ding Li, William Marshall, Xuanyu Zhang, Yihan Wan, Yunhao Tang.
 1. **[Wav2Vec2](https://huggingface.co/docs/transformers/model_doc/wav2vec2)** (from Facebook AI) released with the paper [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://huggingface.co/papers/2006.11477) by Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, Michael Auli.
 1. **[Wav2Vec2-BERT](https://huggingface.co/docs/transformers/main/model_doc/wav2vec2-bert)** (from Meta AI) released with the paper [Seamless: Multilingual Expressive and Streaming Speech Translation](https://ai.meta.com/research/publications/seamless-multilingual-expressive-and-streaming-speech-translation/) by the Seamless Communication team.
 1. **[WavLM](https://huggingface.co/docs/transformers/model_doc/wavlm)** (from Microsoft Research) released with the paper [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://huggingface.co/papers/2110.13900) by Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, Jian Wu, Long Zhou, Shuo Ren, Yanmin Qian, Yao Qian, Jian Wu, Michael Zeng, Furu Wei.

docs/snippets/2_installation.snippet

@@ -7,6 +7,6 @@ npm i @huggingface/transformers
 Alternatively, you can use it in vanilla JS, without any bundler, by using a CDN or static hosting. For example, using [ES Modules](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Modules), you can import the library with:
 ```html
 <script type="module">
-    import { pipeline } from 'https://cdn.jsdelivr.net/npm/@huggingface/transformers@3.6.2';
+    import { pipeline } from 'https://cdn.jsdelivr.net/npm/@huggingface/transformers@3.7.0';
 </script>
 ```

docs/snippets/4_custom-usage.snippet

@@ -1,6 +1,6 @@
 
 
-By default, Transformers.js uses [hosted pretrained models](https://huggingface.co/models?library=transformers.js) and [precompiled WASM binaries](https://cdn.jsdelivr.net/npm/@huggingface/transformers@3.6.2/dist/), which should work out-of-the-box. You can customize this as follows:
+By default, Transformers.js uses [hosted pretrained models](https://huggingface.co/models?library=transformers.js) and [precompiled WASM binaries](https://cdn.jsdelivr.net/npm/@huggingface/transformers@3.7.0/dist/), which should work out-of-the-box. You can customize this as follows:
 
 ### Settings